Network resource configuration method, device, equipment, medium and product

Abstract

The present disclosure provides a network resource configuration method, device, equipment, medium and product, wherein the network resource configuration method includes: extracting features of traffic forwarded by CDN to determine feature vectors corresponding to the traffic; inputting feature vectors into a neural network model for recognition processing; generating configuration information of a cloud function according to the result of the recognition processing; and adapting the resource pool of the cloud function to the demand based on the configuration information, and the cloud function is configured to perform computational processing on the CDN service. Through the embodiments of the present disclosure, the cloud function service can be called for elastic preheating caching, thereby improving the data interaction performance and reliability of the deployed nodes.

Description

Background Art

[0002] At present, in the practice of image and video CDN preheating, services are basically provided by using fixed CDN nodes and partial PCDN service support. Cloud functions are appropriately introduced for customers to provide CDN+serverless combination services, which can effectively avoid the peak and valley problems of traffic forwarding and provide elastic, volume-based empowerment services.

[0003] In related technologies, images and videos require high-bandwidth resources and are facing more and more demands for secondary editing and processing. Currently, there are generally two processing methods to meet such demands. The first is to access the source site through the CDN node, and the source site completes the processing operation. The second is to process in the forwarding node cluster.

[0004] However, there are at least the following technical problems in the related art:

[0005] (1) Multiple CDN nodes report at the same time, which will occupy a large amount of bandwidth and computing resources of the origin site.

[0006] (2) The computing resources of the edge node cluster are insufficient, which affects the forwarding performance of other business resources.

[0007] (3) If it is necessary to preheat the cache according to the habits of the user group, especially for video content currently oriented to the vicinity of the region, if the preheating process is performed in an unordered manner and without considering the traffic bandwidth limitation, the cache content with a large amount of data is likely to cause a waste of preheating resources and cache resources of the edge node.

[0008] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0009] The purpose of the present disclosure is to provide a network resource configuration method, apparatus, device, medium and product, which are used to overcome the problems of network resource waste caused by the limitations and defects of related technologies at least to a certain extent.

[0010] According to a first aspect of an embodiment of the present disclosure, a network resource configuration method is provided, comprising: extracting features of traffic forwarded by a CDN to determine a feature vector corresponding to the traffic; inputting the feature vector into a neural network model for recognition processing; generating configuration information of the cloud function based on a result of the recognition processing; and performing demand adaptation on a resource pool of the cloud function based on the configuration information, wherein the cloud function is configured to perform computational processing on the CDN service.

[0011] In an exemplary embodiment of the present disclosure, feature extraction is performed on traffic forwarded by a CDN to determine a feature vector corresponding to the traffic, including:

[0012] Triggering the ELK system associated with the CDN to collect traffic forwarding records of the CDN within a specified time;

[0013] Parsing the traffic forwarding record to determine specified parameters of the traffic forwarded by the CDN, the specified parameters including at least one of a timestamp, a node identifier, a node server scale, a data type, a cache data volume, a cache hit rate, a resource operation identifier, and a region identifier;

[0014] The specified parameters obtained by analysis are fused to obtain the feature vector.

[0015] In an exemplary embodiment of the present disclosure, inputting the feature vector into a neural network model for recognition processing includes:

[0016] The feature vector is input into the LSTM neural network model for recognition processing, and the recognition processing result output by the LSTM neural network model includes at least one of a timestamp, a CDN node identifier, and a cloud function deployment information.

[0017] In an exemplary embodiment of the present disclosure, generating the configuration information of the cloud function according to the result of the identification processing includes:

[0018] Determine the CDN for which resource configuration is to be performed according to the CDN node identifier;

[0019] Based on the timestamp and the cloud function deployment information, preheating configuration information of the cloud function corresponding to the CDN to be resource configured is generated.

[0020] In an exemplary embodiment of the present disclosure, generating the configuration information of the cloud function according to the result of the identification processing further includes:

[0021] The first serverless resource configuration information of the cloud function is generated according to the result of the identification processing, and the first serverless resource configuration information is used to provide standard serverless resources to the CDN, and the standard serverless resources are used to elastically expand the capacity of the corresponding regional CDN.

[0022] In an exemplary embodiment of the present disclosure, generating the configuration information of the cloud function according to the result of the identification processing further includes:

[0023] The second serverless resource configuration information of the cloud function is generated according to the result of the identification processing, and the second serverless resource configuration information is used to provide enhanced serverless resources to the CDN, and the enhanced serverless resources are used to improve the image traffic caching performance of the CDN.

[0024] In an exemplary embodiment of the present disclosure, the CDN includes at least one node among an edge CDN, a regional CDN and a secondary CDN.

[0025] According to a second aspect of an embodiment of the present disclosure, a network resource configuration device is provided, including:

[0026] An extraction module, configured to extract features of the traffic forwarded by the CDN to determine a feature vector corresponding to the traffic;

[0027] A recognition module, configured to input the feature vector into a neural network model for recognition processing;

[0028] A generation module, configured to generate configuration information of the cloud function according to the result of the identification processing;

[0029] A configuration module is configured to perform demand adaptation on the resource pool of the cloud function based on the configuration information, and the cloud function is configured to perform computational processing on the service of the CDN.

[0030] According to a third aspect of the present disclosure, there is provided an electronic device, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute any one of the methods described above based on instructions stored in the memory.

[0031] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a program is stored, and when the program is executed by a processor, the network resource configuration method as described in any one of the above is implemented.

[0032] According to a fifth aspect of the present disclosure, there is provided a computer program product, comprising a computer program, characterized in that when the computer program is executed by a processor, the network resource configuration method as described in any one of the above is implemented.

[0033] The disclosed embodiment extracts features from the traffic forwarded by the CDN to determine a feature vector corresponding to the traffic, and inputs the feature vector into a neural network model for identification processing, and then generates configuration information of the cloud function according to the result of the identification processing, and finally adapts the demand for the resource pool of the cloud function based on the configuration information. The cloud function is configured to perform computational processing on the service of the CDN, thereby optimizing the configuration of the cloud function resource pool, and calling the cloud function service for elastic preheating caching in the CDN forwarding traffic solution, thereby improving the data interaction performance and reliability of the deployed nodes.

[0034] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0036] Figure 1 A schematic diagram showing an exemplary system architecture to which the network resource configuration solution of an embodiment of the present invention can be applied;

[0037] Figure 2 is a flow chart of a network resource configuration method in an exemplary embodiment of the present disclosure;

[0038] Figure 3 is a flow chart of another network resource configuration method in an exemplary embodiment of the present disclosure;

[0039] Figure 4 is a flow chart of another network resource configuration method in an exemplary embodiment of the present disclosure;

[0040] Figure 5 is a flow chart of another network resource configuration method in an exemplary embodiment of the present disclosure;

[0041] Figure 6 is a flow chart of another network resource configuration method in an exemplary embodiment of the present disclosure;

[0042] Figure 7 is a flow chart of another network resource configuration method in an exemplary embodiment of the present disclosure;

[0043] Figure 8 is a schematic diagram of an architecture of a network resource configuration solution in an exemplary embodiment of the present disclosure;

[0044] Fig. 9 is a flowchart of a network resource configuration solution in an exemplary embodiment of the present disclosure;

[0045] Fig.10 is a block diagram of a network resource configuration device in an exemplary embodiment of the present disclosure;

[0046] Fig.11 is a block diagram of an electronic device in an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0047] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0048] In addition, the accompanying drawings are only schematic diagrams of the present disclosure, and the same reference numerals in the drawings represent the same or similar parts, so their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0049] The technical terms involved in the embodiments of the present disclosure include:

[0050] CDN (Content Delivery Network): A content distribution network is a distributed network built and covered on the bearer network and composed of edge node server clusters distributed in different regions.

[0051] Serverless (serverless computing): Serverless architecture is a design concept that uses FaaS (function as a service) and BaaS (backend service) services to solve problems.

[0052] LSTM (Long Short-Term Memory): is a special type of recurrent neural network (RNN), which is particularly suitable for processing sequence data, such as time series, text data, etc., but not limited to this.

[0053] Figure 1 A schematic diagram showing an exemplary system architecture to which the network resource configuration solution according to an embodiment of the present invention can be applied.

[0054] like Figure 1 As shown, the system architecture 100 may include one or more of terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0055] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. According to the implementation requirements, there may be any number of terminal devices, networks and servers. For example, the server 105 may be a server cluster composed of multiple servers.

[0056] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, portable computers, desktop computers, etc.

[0057] In some embodiments, the network resource configuration method provided in the embodiments of the present invention is generally executed by the server 105. Accordingly, the network resource configuration device is generally set in the terminal device 103 (or the terminal device 101 or 102). In other embodiments, some terminals may have similar functions to the server device to execute the method.

[0058] The exemplary embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0059] Figure 2 is a flow chart of a network resource configuration method in an exemplary embodiment of the present disclosure.

[0060] refer to Figure 2 , the network resource configuration method may include:

[0061] Step S202: extracting features from the traffic forwarded by the CDN to determine a feature vector corresponding to the traffic.

[0062] In an exemplary embodiment of the present disclosure, CDN nodes are generally distributed in different geographical locations and network environments, and their main function is to cache and distribute content to accelerate user access to the content.

[0063] In an exemplary embodiment of the present disclosure, CDN nodes can be divided into the following types:

[0064] (1) Edge nodes: These are nodes closest to users. When a user initiates a content request, the edge node will respond first. If the content required by the user has been cached in the edge node, the content can be directly returned to the user, greatly reducing the delay in data transmission and improving access speed.

[0065] (2) Intermediate node: located between the edge node and the source station, it plays the role of data transfer and distribution.

[0066] (3) Core nodes: They are usually closely connected to the source station and are responsible for obtaining the latest content from the source station and distributing it to intermediate nodes and edge nodes.

[0067] Step S204: input the feature vector into a neural network model for recognition processing.

[0068] Step S206: Generate configuration information of the cloud function based on the result of the identification processing.

[0069] In an exemplary embodiment of the present disclosure, the configuration information of the cloud function includes but is not limited to:

[0070] (1) Set the operating environment of the cloud function, such as specifying the runtime version, memory size, etc.

[0071] (2) Configure the triggering method of the cloud function, such as HTTP triggering, timed triggering, message queue triggering, etc.

[0072] (3) Upload cloud function code: Upload the written cloud function code to the cloud platform.

[0073] (4) Set input and output parameters: Define the input parameters and expected output format of the cloud function.

[0074] (5) Configure permissions and access control: Set appropriate permissions for cloud functions as needed to control access to related resources.

[0075] Step S208: adapt the resource pool of the cloud function to the demand based on the configuration information, and the cloud function is configured to perform computational processing on the CDN service.

[0076] In an exemplary embodiment of the present disclosure, the resource pool of the cloud function is adapted to the needs based on the configuration information, that is, the resource pool of the cloud function is updated and configured, and then the updated cloud function can be used in conjunction with the CDN node to achieve a more optimized service architecture.

[0077] In an exemplary embodiment of the present disclosure, when there is no cached content requested by the user in the CDN node, the updated cloud function may be triggered to dynamically generate the corresponding content. For example, according to the user's request parameters, the cloud function can generate personalized pictures, page fragments, etc. in real time and quickly distribute them to users through the CDN node.

[0078] In an exemplary embodiment of the present disclosure, the updated cloud function can also be used to process CDN-related configuration and management tasks, such as dynamically adjusting the CDN cache strategy according to traffic conditions, or performing corresponding processing and alarming when a CDN node fails.

[0079] The disclosed embodiment extracts features from the traffic forwarded by the CDN to determine a feature vector corresponding to the traffic, and inputs the feature vector into a neural network model for identification processing, and then generates configuration information of the cloud function according to the result of the identification processing, and finally adapts the demand for the resource pool of the cloud function based on the configuration information. The cloud function is configured to perform computational processing on the service of the CDN, thereby optimizing the configuration of the cloud function resource pool, and calling the cloud function service for elastic preheating caching in the CDN forwarding traffic solution, thereby improving the data interaction performance and reliability of the deployed nodes.

[0080] The following describes in detail each step of the network resource configuration method.

[0081] In an exemplary embodiment of the present disclosure, Figure 3 As shown, feature extraction is performed on the traffic forwarded by the CDN to determine that the feature vector corresponding to the traffic includes:

[0082] Step S302, triggering the ELK system associated with the CDN to collect traffic forwarding records of the CDN within a specified time.

[0083] In an exemplary embodiment of the present disclosure, ELK is a combination of three open source software, namely Elasticsearch, Logstash and Kibana, which provides a complete set of log collection, analysis and display solutions, suitable for real-time data retrieval and analysis scenarios, wherein Logstash collects logs generated by application servers, formats them and outputs them to Elasticsearch cluster nodes, Elasticsearch indexes and stores the formatted data, Kibana queries data from the Elasticsearch cluster nodes and generates charts, which are then returned to the browser, so that users can view the interface display online.

[0084] Step S304, parsing the traffic forwarding record to determine the specified parameters of the traffic forwarded by the CDN, the specified parameters including at least one of a timestamp, a node identifier, a node server scale, a data type, a cache data volume, a cache hit rate, a resource operation identifier, and a region identifier.

[0085] In an exemplary embodiment of the present disclosure, the timestamp in the specified parameter is used to record the time information of collecting the specified parameter.

[0086] In an exemplary embodiment of the present disclosure, the node identifier is used to indicate the identity information of the CDN.

[0087] In an exemplary embodiment of the present disclosure, the data type includes images, videos, files, etc., but is not limited thereto.

[0088] Step S306: performing fusion processing on the designated parameters obtained by parsing to obtain the feature vector.

[0089] In an exemplary embodiment of the present disclosure, the feature vector is obtained by fusing the specified parameters obtained by analysis, which is more conducive to improving the accuracy and reliability of model recognition.

[0090] In an exemplary embodiment of the present disclosure, Figure 4 As shown, inputting the feature vector into the neural network model for recognition processing includes:

[0091] Step S402: input the feature vector into the LSTM neural network model for recognition processing, and the recognition processing result output by the LSTM neural network model includes at least one of a timestamp, a CDN node identifier, and a cloud function deployment information.

[0092] In an exemplary embodiment of the present disclosure, the timestamp in the result of the identification process is used to indicate the time information for adapting the resource pool of the cloud function based on the cloud function deployment information.

[0093] In an exemplary embodiment of the present disclosure, Figure 5 As shown, the configuration information of the cloud function generated according to the result of the identification processing includes:

[0094] Step S502: determining the CDN for which resource configuration is to be performed according to the CDN node identifier.

[0095] Step S504: Generate preheating configuration information of the cloud function corresponding to the CDN to be resource configured based on the timestamp and the cloud function deployment information.

[0096] In an exemplary embodiment of the present disclosure, Figure 6 As shown, the configuration information of the cloud function generated according to the result of the identification processing also includes:

[0097] Step S602: Generate first serverless resource configuration information of the cloud function according to the result of the identification processing, wherein the first serverless resource configuration information is used to provide standard serverless resources to the CDN, and the standard serverless resources are used to elastically expand the capacity of the corresponding regional CDN.

[0098] In an exemplary embodiment of the present disclosure, the first serverless resource configuration information of the cloud function is generated according to the result of the identification processing to achieve elastic expansion of the corresponding regional CDN, thereby ensuring the standard forwarding performance of the CDN.

[0099] In an exemplary embodiment of the present disclosure, Figure 7 As shown, the configuration information of the cloud function generated according to the result of the identification processing also includes:

[0100] Step S702: Generate second serverless resource configuration information of the cloud function according to the result of the identification processing, wherein the second serverless resource configuration information is used to provide enhanced serverless resources to the CDN, and the enhanced serverless resources are used to improve the image traffic caching performance of the CDN.

[0101] In an exemplary embodiment of the present disclosure, by generating a second serverless resource configuration signal of the cloud function according to the result of the identification processing, the cache processing capability of resources such as pictures and videos during peak hours is improved.

[0102] In an exemplary embodiment of the present disclosure, the CDN includes at least one node among an edge CDN, a regional CDN and a secondary CDN.

[0103] In an exemplary embodiment of the present disclosure, edge nodes and regional nodes essentially belong to the category of regional nodes, and a multi-level cache forwarding structure is formed according to the popularity of the edge, which facilitates analysis of CDN nodes within the regional range.

[0104] In an exemplary embodiment of the present disclosure, the secondary node is a CDN aggregation and forwarding node, which is a service node connecting a source station or a national node to an edge node.

[0105] In an exemplary embodiment of the present disclosure, Figure 8 As shown, the architecture of the network resource configuration solution disclosed in the present invention includes an edge data center 802, ELK log collection 804, regional feature deployment 806, a cloud function resource pool 808, and a source station set 810, but is not limited thereto.

[0106] In an exemplary embodiment of the present disclosure, Figure 8 As shown, the architecture of the network resource configuration solution disclosed in the present invention monitors and counts the CDN forwarding traffic of the hotspot edge node, extracts features to form feature vectors, and inputs the feature vectors into the LSTM model to obtain the cloud function deployment time prediction model for resources such as images and videos in the hotspot area, and adapts the cloud function resource pool to the needs according to the editing classification of the image or video. The specific execution process includes:

[0107] In an exemplary embodiment of the present disclosure, ELK log collection 804 collects node logs in units of days, and parses and counts CDN traffic forwarding records within two months.

[0108] In an exemplary embodiment of the present disclosure, with reference to the time interval of 95 broadband statistics, a feature vector of forwarding traffic is formed with 5 minutes as the statistical dimension, including at least timestamp, node identifier, node server scale, data type, cache data volume, cache hit rate, resource operation identifier, and regional identifier. After the fusion of historical statistical data and data processing, it is sent to the regional training cluster for LSTM model training;

[0109] In an exemplary embodiment of the present disclosure, LSTM training inference forms an output vector including a timestamp, a node identifier, a cloud function deployment parameter list, and a cloud function preheating cache parameter list, and the user's proximal CDN node forms a CDN node configuration file based on the output vector;

[0110] In an exemplary embodiment of the present disclosure, the node traffic is classified according to the cycle reasoning time to meet the effective utilization of the resource pool. At the same time, iterative training is performed in a two-week cycle in combination with historical statistical data to update the CDN node cloud function deployment strategy and preheating configuration.

[0111] In an exemplary embodiment of the present disclosure, the network resource configuration scheme of the present disclosure obtains the cache and traffic forwarding characteristics of different CDN nodes for regional video image needs within a certain period of time through LSTM training, and reasonably uses cloud functions to complete the corresponding node service support.

[0112] In an exemplary embodiment of the present disclosure, the network resource configuration scheme of the present disclosure is aimed at the increasing number of operation requests for video images. Through traffic request analysis, cloud functions are used to complete preheating processing near the client, thereby reducing the response of the source station to different operation resources.

[0113] In an exemplary embodiment of the present disclosure, the network resource configuration scheme of the present disclosure predicts certain types of pictures and videos with high access statistics in the local area through traffic analysis, and prepares resources for peak time after the cloud function is preheated.

[0114] In an exemplary embodiment of the present disclosure, the network resource configuration solution of the present disclosure is aimed at preheating image and video resources within a regional range in a CDN edge node content forwarding scenario.

[0115] In an exemplary embodiment of the present disclosure, the network resource configuration scheme of the present disclosure utilizes a remote computing cluster to analyze the time and area characteristics of the CDN in the regional scope when operating to forward image or video resources, combines the cloud function characteristics, deploys the preheating strategy of the corresponding node, and realizes the elastic resource utilization of the node.

[0116] In an exemplary embodiment of the present disclosure, edge nodes and regional nodes essentially belong to the category of regional nodes, and a multi-level cache forwarding structure is formed according to the popularity of the edge, which facilitates analysis of CDN nodes within the regional range.

[0117] In an exemplary embodiment of the present disclosure, the secondary node is a CDN aggregation and forwarding node, which is a service node connecting a source station or a national node to an edge node.

[0118] In an exemplary embodiment of the present disclosure, the far edge data center 802 is used to perform training and reasoning on edge node behaviors in a regional scope, and provide relatively sufficient computing resources.

[0119] In an exemplary embodiment of the present disclosure, the cloud function resource pool 808 provides elastically scalable serverless resources for edge nodes, and can provide a variety of service elastic instances such as standard and high-computing types.

[0120] In an exemplary embodiment of the present disclosure, Fig. 9 As shown, the network resource configuration scheme disclosed in the present invention includes the following steps:

[0121] In step S902, the ELK system collects and stores logs to form traffic statistics at 5-minute intervals, and inputs them into the data center for data cleaning. The feature vector group is extracted, including timestamp, node ID, node server scale, data type, cache data volume, cache hit rate, resource operation ID, and region ID. Combined with the vector data of the past two months, model training and fine-tuning are formed in a 15-day cycle.

[0122] Step S904, input vector extraction, that is, for the trained model and the input vector, output an output vector for the regional node, including a timestamp, a node identifier, a cloud function deployment parameter list, and a cloud function preheating cache parameter list.

[0123] In an exemplary embodiment of the present disclosure, a configuration file in a standard format is formed according to parameter contents and distributed, and the cloud function pool is divided into two categories for deployment preheating to improve CDN preheating cache performance.

[0124] In an exemplary embodiment of the present disclosure, the preheating strategy belongs to traffic forwarding preheating to provide standard serverless resources and complete the elastic expansion of the corresponding regional nodes. The preheating strategy focuses on responding to the cache resource operation requirements, providing computing-enhanced serverless resources, and providing image and video processing cache capabilities during peak demand periods.

[0125] Step S906, determine whether it is model training, if so, execute step S908, if not, execute step S914.

[0126] Step S908, clean the log data, form a standard input vector group, combine it with the historical data vector, and perform LSTM model training.

[0127] Step S910: LSTM model training is completed.

[0128] Step S912: deploy in a far edge data center.

[0129] Step S914, input the inference vector into the trained model to obtain the output vector information of cloud function deployment and preheating.

[0130] Step S916, based on the CDN node configuration file template and the CDN preheating resource configuration template, the conversion module converts the parameter information in the output vector into a standard file for node configuration preheating, and then sends it to the corresponding CDN node.

[0131] Step S918, the cloud function resource pool parses the node standard configuration file and the preheating configuration file to complete the preparation of the corresponding cloud function resources for the customer.

[0132] Step S920: The CDN node in the corresponding region calls the cloud function to complete the elastic resource service support according to the configuration strategy.

[0133] The embodiments of the present disclosure provide a CDN cloud function elastic preheating solution based on LSTM analysis and prediction. In the process of edge traffic forwarding, the current CDN uses smaller node servers on the one hand, and uses a PCDN-like approach on the other hand to increase the resource edge forwarding capability. The introduction of cloud functions provides preheating forwarding capabilities to the user side according to the changes in traffic peaks and valleys, which can meet the user side's forwarding and acquisition needs for high-performance demand resources such as videos and images with limited resources.

[0134] Corresponding to the above method embodiments, the present disclosure also provides a network resource configuration device, which can be used to execute the above method embodiments.

[0135] Fig.10 It is a block diagram of a network resource configuration device in an exemplary embodiment of the present disclosure.

[0136] refer to Fig.10 , the network resource configuration device 1000 may include:

[0137] The extraction module 1002 is configured to perform feature extraction on the traffic forwarded by the CDN to determine a feature vector corresponding to the traffic.

[0138] The recognition module 1004 is configured to input the feature vector into a neural network model for recognition processing.

[0139] The generation module 1006 is configured to generate the configuration information of the cloud function according to the result of the identification processing.

[0140] The configuration module 1008 is configured to perform demand adaptation on the resource pool of the cloud function based on the configuration information, and the cloud function is configured to perform computational processing on the service of the CDN.

[0141] In an exemplary embodiment of the present disclosure, the extraction module 1002 is further configured to:

[0142] Triggering the ELK system associated with the CDN to collect traffic forwarding records of the CDN within a specified time;

[0143] Parsing the traffic forwarding record to determine specified parameters of the traffic forwarded by the CDN, the specified parameters including at least one of a timestamp, a node identifier, a node server scale, a data type, a cache data volume, a cache hit rate, a resource operation identifier, and a region identifier;

[0144] The specified parameters obtained by analysis are fused to obtain the feature vector.

[0145] In an exemplary embodiment of the present disclosure, the identification module 1004 is further configured to:

[0146] The feature vector is input into the LSTM neural network model for recognition processing, and the recognition processing result output by the LSTM neural network model includes at least one of a timestamp, a CDN node identifier, and a cloud function deployment information.

[0147] In an exemplary embodiment of the present disclosure, the generating module 1006 is further configured to:

[0148] Determine the CDN for which resource configuration is to be performed according to the CDN node identifier;

[0149] Based on the timestamp and the cloud function deployment information, preheating configuration information of the cloud function corresponding to the CDN to be resource configured is generated.

[0150] In an exemplary embodiment of the present disclosure, the generating module 1006 is further configured to:

[0151] The first serverless resource configuration information of the cloud function is generated according to the result of the identification processing, and the first serverless resource configuration information is used to provide standard serverless resources to the CDN, and the standard serverless resources are used to elastically expand the capacity of the corresponding regional CDN.

[0152] In an exemplary embodiment of the present disclosure, the generating module 1006 is further configured to:

[0153] The second serverless resource configuration information of the cloud function is generated according to the result of the identification processing, and the second serverless resource configuration information is used to provide enhanced serverless resources to the CDN, and the enhanced serverless resources are used to improve the image traffic caching performance of the CDN.

[0154] In an exemplary embodiment of the present disclosure, the CDN includes at least one node among an edge CDN, a regional CDN and a secondary CDN.

[0155] Since the functions of the device 1000 have been described in detail in the corresponding method embodiments, the present disclosure will not elaborate on them here.

[0156] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0157] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0158] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0159] Refer to the following Fig.11 The electronic device 1100 according to this embodiment of the present invention is described. Fig.11 The electronic device 1100 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0160] like Fig.11 As shown, the electronic device 1100 is in the form of a general computing device. The components of the electronic device 1100 may include but are not limited to: at least one processing unit 1110, at least one storage unit 1120, and a bus 1130 connecting different system components (including the storage unit 1120 and the processing unit 1110).

[0161] The storage unit stores program codes, which can be executed by the processing unit 1110, so that the processing unit 1110 performs the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification. For example, the processing unit 1110 can perform the method shown in the embodiment of the present disclosure.

[0162] The storage unit 1120 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 11201 and / or a cache storage unit 11202 , and may further include a read-only storage unit (ROM) 11203 .

[0163] The storage unit 1120 may also include a program / utility 11204 having a set (at least one) of program modules 11205, such program modules 11205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0164] Bus 1130 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0165] The electronic device 1100 may also communicate with one or more external devices 1140 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1100, and / or may communicate with any device that enables the electronic device 1100 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 1150. In addition, the electronic device 1100 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 1160. As shown, the network adapter 1160 communicates with other modules of the electronic device 1100 through a bus 1130. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0166] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0167] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0168] The program product for implementing the above method according to an embodiment of the present invention can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0169] Among them, the readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0170] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0171] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0172] In an exemplary embodiment of the present disclosure, a computer program product is also provided, which can be loaded or stored in any combination of one or more readable media, and can be written in any combination of one or more programming languages ​​to perform the program code of the present invention, wherein the programming language includes an object-oriented programming language, such as Java, C++, etc., and also includes a conventional procedural programming language, such as "C" language or similar programming language. The program code can be executed completely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on the remote computing device, or completely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0173] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0174] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are to be considered exemplary only, and the true scope and concept of the present disclosure are indicated by the claims.

Claims

1. A network resource configuration method, characterized in that: include: Extracting features of the traffic forwarded by the CDN to determine a feature vector corresponding to the traffic; Inputting the feature vector into a neural network model for recognition processing; Generate configuration information of the cloud function according to the result of the identification processing; The resource pool of the cloud function is adapted to the needs based on the configuration information, and the cloud function is configured to perform computational processing on the service of the CDN.

2. The network resource configuration method according to claim 1, characterized in that: Feature extraction is performed on the traffic forwarded by the CDN to determine the feature vector corresponding to the traffic, including: Triggering the ELK system associated with the CDN to collect traffic forwarding records of the CDN within a specified time; Parsing the traffic forwarding record to determine specified parameters of the traffic forwarded by the CDN, the specified parameters including at least one of a timestamp, a node identifier, a node server scale, a data type, a cache data volume, a cache hit rate, a resource operation identifier, and a region identifier; The specified parameters obtained by analysis are fused to obtain the feature vector.

3. The network resource configuration method according to claim 1, characterized in that: Inputting the feature vector into the neural network model for recognition processing includes: The feature vector is input into the LSTM neural network model for recognition processing, and the recognition processing result output by the LSTM neural network model includes at least one of a timestamp, a CDN node identifier, and a cloud function deployment information.

4. The network resource configuration method according to claim 3, characterized in that: The configuration information of the cloud function generated according to the result of the identification processing includes: Determine the CDN for which resource configuration is to be performed according to the CDN node identifier; Based on the timestamp and the cloud function deployment information, preheating configuration information of the cloud function corresponding to the CDN to be resource configured is generated.

5. The network resource configuration method according to any one of claims 1 to 4, characterized in that: Generating the configuration information of the cloud function according to the result of the identification processing also includes: The first serverless resource configuration information of the cloud function is generated according to the result of the identification processing, and the first serverless resource configuration information is used to provide standard serverless resources to the CDN, and the standard serverless resources are used to elastically expand the capacity of the corresponding regional CDN.

6. The network resource configuration method according to any one of claims 1 to 4, characterized in that: Generating the configuration information of the cloud function according to the result of the identification processing also includes: The second serverless resource configuration information of the cloud function is generated according to the result of the identification processing, and the second serverless resource configuration information is used to provide enhanced serverless resources to the CDN, and the enhanced serverless resources are used to improve the image traffic caching performance of the CDN.

7. The network resource configuration method according to any one of claims 1 to 4, characterized in that: The CDN includes at least one node among edge CDN, regional CDN and secondary CDN.

8. A network resource configuration device, characterized in that: include: An extraction module, configured to extract features of the traffic forwarded by the CDN to determine a feature vector corresponding to the traffic; A recognition module, configured to input the feature vector into a neural network model for recognition processing; A generation module, configured to generate configuration information of a cloud function according to a result of the identification process; A configuration module is configured to perform demand adaptation on the resource pool of the cloud function based on the configuration information, and the cloud function is configured to perform computational processing on the service of the CDN.

9. An electronic device, characterized in that: include: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the network resource configuration method according to any one of claims 1 to 7 based on instructions stored in the memory.

10. A computer-readable storage medium having a program stored thereon, wherein when the program is executed by a processor, the network resource configuration method according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the network resource configuration method according to any one of claims 1 to 7 is implemented.

Images